English
Related papers

Related papers: Concept-Based Explanations to Test for False Causa…

200 papers

Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…

Machine Learning · Computer Science 2020-12-21 Zhao Wang , Aron Culotta

In standard classification, we typically treat class categories as independent of one-another. In many problems, however, we would be neglecting the natural relations that exist between categories, which are often dictated by an underlying…

Computer Vision and Pattern Recognition · Computer Science 2020-06-25 Muhamedrahimov Raouf , Bar Amir , Akselrod-Ballin Ayelet

Determining the plausibility of causal relations between clauses is a commonsense reasoning task that requires complex inference ability. The general approach to this task is to train a large pretrained language model on a specific dataset.…

Computation and Language · Computer Science 2021-01-14 Ieva Staliūnaitė , Philip John Gorinski , Ignacio Iacobacci

While argument mining has achieved significant success in classifying argumentative relations between statements (support, attack, and neutral), we have a limited computational understanding of logical mechanisms that constitute those…

Computation and Language · Computer Science 2021-05-18 Yohan Jo , Seojin Bang , Chris Reed , Eduard Hovy

Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging. This paper presents an in-depth…

Machine Learning · Computer Science 2020-09-30 Dominique Mercier , Shoaib Ahmed Siddiqui , Andreas Dengel , Sheraz Ahmed

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Zaiying Zhao , Soichiro Kumano , Toshihiko Yamasaki

Bias in Large Language Models (LLMs) significantly undermines their reliability and fairness. We focus on a common form of bias: when two reference concepts in the model's concept space, such as sentiment polarities (e.g., "positive" and…

Computation and Language · Computer Science 2025-05-22 Lang Gao , Kaiyang Wan , Wei Liu , Chenxi Wang , Zirui Song , Zixiang Xu , Yanbo Wang , Veselin Stoyanov , Xiuying Chen

This paper presents a rich knowledge representation language aimed at formalizing causal knowledge. This language is used for accurately and directly formalizing common benchmark examples from the literature of actual causality. A…

Artificial Intelligence · Computer Science 2023-06-07 Michael Gelfond , Jorge Fandinno , Evgenii Balai

Motivated by the desire to generate labels for real-time data we develop a method to estimate the dependency structure and accuracy of weak supervision sources incrementally. Our method first estimates the dependency structure associated…

Machine Learning · Computer Science 2022-05-12 Richard Gresham Correro

A complementary label (CL) simply indicates an incorrect class of an example, but learning with CLs results in multi-class classifiers that can predict the correct class. Unfortunately, the problem setting only allows a single CL for each…

Machine Learning · Computer Science 2022-08-09 Lei Feng , Takuo Kaneko , Bo Han , Gang Niu , Bo An , Masashi Sugiyama

While in-context learning with large language models (LLMs) has shown impressive performance, we have discovered a unique miscalibration behavior where both correct and incorrect predictions are assigned the same level of confidence. We…

Computation and Language · Computer Science 2024-10-04 Wei Cheng , Tianlu Wang , Yanmin Ji , Fan Yang , Keren Tan , Yiyu Zheng

The subjective perception of emotion leads to inconsistent labels from human annotators. Typically, utterances lacking majority-agreed labels are excluded when training an emotion classifier, which cause problems when encountering ambiguous…

Computation and Language · Computer Science 2024-10-14 Wen Wu , Bo Li , Chao Zhang , Chung-Cheng Chiu , Qiujia Li , Junwen Bai , Tara N. Sainath , Philip C. Woodland

We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent factors produces a…

Machine Learning · Computer Science 2020-10-23 Matthew O'Shaughnessy , Gregory Canal , Marissa Connor , Mark Davenport , Christopher Rozell

Comparable texts are topic-aligned documents in multiple languages that are not direct translations. They are valuable for understanding how a topic is discussed across languages. This research studies differences in sentiments and emotions…

Computation and Language · Computer Science 2025-08-06 Motaz Saad , David Langlois , Kamel Smaili

Natural Language Processing prides itself to be an empirically-minded, if not outright empiricist field, and yet lately it seems to get itself into essentialist debates on issues of meaning and measurement ("Do Large Language Models…

Computation and Language · Computer Science 2023-10-30 David Schlangen

Causal inference relies on two fundamental assumptions: ignorability and positivity. We study causal inference when the true confounder value can be expressed as a function of the observed data; we call this setting estimation with…

Methodology · Statistics 2021-02-18 Aahlad Puli , Adler J. Perotte , Rajesh Ranganath

Weighting estimators based on propensity scores are widely used for causal estimation in a variety of contexts, such as observational studies, marginal structural models and interference. They enjoy appealing theoretical properties such as…

Methodology · Statistics 2021-10-06 Linbo Wang , Yuexia Zhang , Thomas S. Richardson , Xiao-Hua Zhou

There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical…

Understanding emotions in natural language is inherently a multi-dimensional reasoning problem, where multiple affective signals interact through context, interpersonal relations, and situational cues. However, most existing emotion…

Computation and Language · Computer Science 2026-04-02 Hemanth Kotaprolu , Kishan Maharaj , Raey Zhao , Abhijit Mishra , Pushpak Bhattacharyya

We investigate how disagreement in natural language inference (NLI) annotation arises. We developed a taxonomy of disagreement sources with 10 categories spanning 3 high-level classes. We found that some disagreements are due to uncertainty…

Computation and Language · Computer Science 2022-09-09 Nan-Jiang Jiang , Marie-Catherine de Marneffe